Title: Adaptive-scale convolutional neural networks for texture image analysis
Authors: Bachir Kaddar; Hadria Fizazi
Addresses: Department of Computer Sciences, Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf, USTO-MB, BP 1505, El M'naouer, 31000 Oran, Algérie ' Department of Computer Sciences, Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf, USTO-MB, BP 1505, El M'naouer, 31000 Oran, Algérie
Abstract: This paper proposes an effective adaptive-scale convolutional neural networks (A-SCNN) for texture image analysis. We combine the multi-scale texture image analysis with the efficient feature space of a convolutional neural network to extract characteristic texture features. These latter encode regions of adaptive sizes centered on each pixel according to different optimal scales reflecting the local structure pattern content. To fix the scale-space values accurately, the Hessian-Laplacian operator is used. Experimental results demonstrate a good performance of the proposed A-SCNN in texture classification. Particularly, the CNN based on the adaptive scale shows promising for irregular texture pattern classification, and the selective sizes of both feature maps and receptive fields can further improve the performance of the classical CNN texture discrimination ability.
Keywords: convolutional neural networks; deep learning; image classification; multi-scale representation; texture discrimination.
International Journal of Signal and Imaging Systems Engineering, 2017 Vol.10 No.5, pp.248 - 256
Received: 14 Nov 2016
Accepted: 26 Jun 2017
Published online: 01 Nov 2017 *